Decaf is DEPRECATED! Please visit for Caffe, the new framework that has all the good things: GPU computation, full train/test scripts, native C++, and an active community!
Switch branches/tags
Nothing to show
Clone or download
Latest commit 6fa4cdf Dec 19, 2015
Failed to load latest commit information.
decaf remove lingering -Wl Dec 19, 2015
.gitignore Initial commit Oct 21, 2013
LICENSE Initial commit Oct 21, 2013 Update Dec 22, 2013 Add dependencies to Nov 27, 2013


Decaf is a framework that implements convolutional neural networks, with the goal of being efficient and flexible. It allows one to easily construct a network in the form of an arbitrary Directed Acyclic Graph (DAG) and to perform end-to-end training.

For more usage check out the wiki. A great place to start is running ImageNet classification on an image.

For the pre-trained imagenet DeCAF feature and its analysis, please see our technical report on arXiv. Please consider citing our paper if you use Decaf in your research:

  title={DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition},
  author={Donahue, Jeff and Jia, Yangqing and Vinyals, Oriol and Hoffman, Judy and Zhang, Ning and Tzeng, Eric and Darrell, Trevor},
  journal={arXiv preprint arXiv:1310.1531},

For Anaconda users experiencing libm error: it is because anaconda ships with a binary that does not support GLIBC_2.15, which gets loaded earlier than the system libm. You can fix this error by you can replacing anaconda's libm file with a newer version.